INDEX

Explanations

quotation marks and their relationships to dialogue or speech constructs

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Text enclosed in quotation marks or angle brackets

np_acts-logits-general · gemini-2.0-flash

Japanese quotation marks 「」

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

requireNonNull

-0.83

 Paglinawan

-0.72

axel

-0.72

 Maynard

-0.72

parer

-0.72

olingo

-0.71

logenetic

-0.70

findpost

-0.70

indrical

-0.69

inFile

-0.68

POSITIVE LOGITS

««

1.05

.«

1.04

?»

1.04

)»

1.03

,»

1.01

»»

0.95

.»

0.94

?«

0.93

(«

0.91

Referències

0.89

Activations Density 0.390%

quotation marks and their relationships to dialogue or speech constructs

Text enclosed in quotation marks or angle brackets

Japanese quotation marks 「」

No Comments

No Known Activations